Amir Feder


2021

pdf bib
Learning and Evaluating a Differentially Private Pre-trained Language Model
Shlomo Hoory | Amir Feder | Avichai Tendler | Alon Cohen | Sofia Erell | Itay Laish | Hootan Nakhost | Uri Stemmer | Ayelet Benjamini | Avinatan Hassidim | Yossi Matias
Proceedings of the Third Workshop on Privacy in Natural Language Processing

Contextual language models have led to significantly better results on a plethora of language understanding tasks, especially when pre-trained on the same data as the downstream task. While this additional pre-training usually improves performance, it can lead to information leakage and therefore risks the privacy of individuals mentioned in the training data. One method to guarantee the privacy of such individuals is to train a differentially-private model, but this usually comes at the expense of model performance. Moreover, it is hard to tell given a privacy parameter $\epsilon$ what was the effect on the trained representation. In this work we aim to guide future practitioners and researchers on how to improve privacy while maintaining good model performance. We demonstrate how to train a differentially-private pre-trained language model (i.e., BERT) with a privacy guarantee of $\epsilon=1$ and with only a small degradation in performance. We experiment on a dataset of clinical notes with a model trained on a target entity extraction task, and compare it to a similar model trained without differential privacy. Finally, we present experiments showing how to interpret the differentially-private representation and understand the information lost and maintained in this process.

pdf bib
Model Compression for Domain Adaptation through Causal Effect Estimation
Guy Rotman | Amir Feder | Roi Reichart
Transactions of the Association for Computational Linguistics, Volume 9

Abstract Recent improvements in the predictive quality of natural language processing systems are often dependent on a substantial increase in the number of model parameters. This has led to various attempts of compressing such models, but existing methods have not considered the differences in the predictive power of various model components or in the generalizability of the compressed models. To understand the connection between model compression and out-of-distribution generalization, we define the task of compressing language representation models such that they perform best in a domain adaptation setting. We choose to address this problem from a causal perspective, attempting to estimate the average treatment effect (ATE) of a model component, such as a single layer, on the model’s predictions. Our proposed ATE-guided Model Compression scheme (AMoC), generates many model candidates, differing by the model components that were removed. Then, we select the best candidate through a stepwise regression model that utilizes the ATE to predict the expected performance on the target domain. AMoC outperforms strong baselines on dozens of domain pairs across three text classification and sequence tagging tasks.1

pdf bib
Learning and Evaluating a Differentially Private Pre-trained Language Model
Shlomo Hoory | Amir Feder | Avichai Tendler | Sofia Erell | Alon Peled-Cohen | Itay Laish | Hootan Nakhost | Uri Stemmer | Ayelet Benjamini | Avinatan Hassidim | Yossi Matias
Findings of the Association for Computational Linguistics: EMNLP 2021

Contextual language models have led to significantly better results, especially when pre-trained on the same data as the downstream task. While this additional pre-training usually improves performance, it can lead to information leakage and therefore risks the privacy of individuals mentioned in the training data. One method to guarantee the privacy of such individuals is to train a differentially-private language model, but this usually comes at the expense of model performance. Also, in the absence of a differentially private vocabulary training, it is not possible to modify the vocabulary to fit the new data, which might further degrade results. In this work we bridge these gaps, and provide guidance to future researchers and practitioners on how to improve privacy while maintaining good model performance. We introduce a novel differentially private word-piece algorithm, which allows training a tailored domain-specific vocabulary while maintaining privacy. We then experiment with entity extraction tasks from clinical notes, and demonstrate how to train a differentially private pre-trained language model (i.e., BERT) with a privacy guarantee of đťś–=1.1 and with only a small degradation in performance. Finally, as it is hard to tell given a privacy parameter đťś– what was the effect on the trained representation, we present experiments showing that the trained model does not memorize private information.

pdf bib
CausaLM: Causal Model Explanation Through Counterfactual Language Models
Amir Feder | Nadav Oved | Uri Shalit | Roi Reichart
Computational Linguistics, Volume 47, Issue 2 - June 2021

Abstract Understanding predictions made by deep neural networks is notoriously difficult, but also crucial to their dissemination. As all machine learning–based methods, they are as good as their training data, and can also capture unwanted biases. While there are tools that can help understand whether such biases exist, they do not distinguish between correlation and causation, and might be ill-suited for text-based models and for reasoning about high-level language concepts. A key problem of estimating the causal effect of a concept of interest on a given model is that this estimation requires the generation of counterfactual examples, which is challenging with existing generation technology. To bridge that gap, we propose CausaLM, a framework for producing causal model explanations using counterfactual language representation models. Our approach is based on fine-tuning of deep contextualized embedding models with auxiliary adversarial tasks derived from the causal graph of the problem. Concretely, we show that by carefully choosing auxiliary adversarial pre-training tasks, language representation models such as BERT can effectively learn a counterfactual representation for a given concept of interest, and be used to estimate its true causal effect on model performance. A byproduct of our method is a language representation model that is unaffected by the tested concept, which can be useful in mitigating unwanted bias ingrained in the data.1

pdf bib
Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions
Daniel Rosenberg | Itai Gat | Amir Feder | Roi Reichart
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

Deep learning algorithms have shown promising results in visual question answering (VQA) tasks, but a more careful look reveals that they often do not understand the rich signal they are being fed with. To understand and better measure the generalization capabilities of VQA systems, we look at their robustness to counterfactually augmented data. Our proposed augmentations are designed to make a focused intervention on a specific property of the question such that the answer changes. Using these augmentations, we propose a new robustness measure, Robustness to Augmented Data (RAD), which measures the consistency of model predictions between original and augmented examples. Through extensive experimentation, we show that RAD, unlike classical accuracy measures, can quantify when state-of-the-art systems are not robust to counterfactuals. We find substantial failure cases which reveal that current VQA systems are still brittle. Finally, we connect between robustness and generalization, demonstrating the predictive power of RAD for performance on unseen augmentations.

pdf bib
Proceedings of the First Workshop on Causal Inference and NLP
Amir Feder | Katherine Keith | Emaad Manzoor | Reid Pryzant | Dhanya Sridhar | Zach Wood-Doughty | Jacob Eisenstein | Justin Grimmer | Roi Reichart | Molly Roberts | Uri Shalit | Brandon Stewart | Victor Veitch | Diyi Yang
Proceedings of the First Workshop on Causal Inference and NLP

2020

pdf bib
Predicting In-Game Actions from Interviews of NBA Players
Nadav Oved | Amir Feder | Roi Reichart
Computational Linguistics, Volume 46, Issue 3 - September 2020

Sports competitions are widely researched in computer and social science, with the goal of understanding how players act under uncertainty. Although there is an abundance of computational work on player metrics prediction based on past performance, very few attempts to incorporate out-of-game signals have been made. Specifically, it was previously unclear whether linguistic signals gathered from players’ interviews can add information that does not appear in performance metrics. To bridge that gap, we define text classification tasks of predicting deviations from mean in NBA players’ in-game actions, which are associated with strategic choices, player behavior, and risk, using their choice of language prior to the game. We collected a data set of transcripts from key NBA players’ pre-game interviews and their in-game performance metrics, totalling 5,226 interview-metric pairs. We design neural models for players’ action prediction based on increasingly more complex aspects of the language signals in their open-ended interviews. Our models can make their predictions based on the textual signal alone, or on a combination of that signal with signals from past-performance metrics. Our text-based models outperform strong baselines trained on performance metrics only, demonstrating the importance of language usage for action prediction. Moreover, the models that utilize both textual input and past-performance metrics produced the best results. Finally, as neural networks are notoriously difficult to interpret, we propose a method for gaining further insight into what our models have learned. Particularly, we present a latent Dirichlet allocation–based analysis, where we interpret model predictions in terms of correlated topics. We find that our best performing textual model is most associated with topics that are intuitively related to each prediction task and that better models yield higher correlation with more informative topics.1